Abstract
Reasonable and effective regional ecological evaluation and analysis methods can be an effective help for urban sustainable development, but there are still some errors in the current ecological prediction and analysis methods. To solve this problem, this paper proposes a prediction method of per capita ecological carrying capacity based on the autoregressive integrated moving average model (ARIMA) and long short-term memory (LSTM). First, the method improves the ecological footprint model based on energy analysis and constructs a comprehensive regional ecological data model; considering the complex characteristics of ecological data set, based on the ARIMA network model and LSTM model, a reliable and efficient big data prediction model of per capita ecological carrying capacity is established by analyzing the linear or nonlinear data sets in the data set. Finally, according to the actual ecological data set collected in Shenzhen, China, the results show that the economic and ecological trend of Shenzhen is generally good.
Highlights
With the rapid growth of population, the natural resources, environment, and economy are becoming increasingly serious, which leads to major problems such as resource depletion, environmental degradation, and ecological damage [1, 2]
Before making a regional analysis, we need to establish a certain evaluation index system, while the traditional evaluation methods of ecological capacity state-space and comprehensive evaluation have some limitations [5–7]. e state-space method is an effective method to quantitatively describe the state of the system in the three-dimensional Euclidean space, but the state-space method can only judge whether the study area is overloaded and cannot give the specific ecological carrying capacity [8]. e comprehensive evaluation method is vulnerable to human subjective factors when constructing a certain evaluation index system [9]
In view of the problems existing in the current analysis methods, in order to more accurately analyze the regional per capita ecological carrying capacity, this paper proposes a new ecological footprint analysis method based on the big data technology
Summary
With the rapid growth of population, the natural resources, environment, and economy are becoming increasingly serious, which leads to major problems such as resource depletion, environmental degradation, and ecological damage [1, 2]. In Reference [16], an artificial bee colony algorithm is used to optimize the radial basis function neural network, and a new prediction model of urban ecological carrying capacity is constructed, which provides a certain theoretical basis for the government’s sustainable development decision. In view of the problems existing in the current analysis methods, in order to more accurately analyze the regional per capita ecological carrying capacity, this paper proposes a new ecological footprint analysis method based on the big data technology. In view of the complex characteristics of big data of ecological footprint, this paper improves the long short-term memory (LSTM) prediction network based on the ARIMA and comprehensively analyzes the linear and nonlinear characteristics of ecological data to achieve the efficient prediction of the ecological capacity in the study area. E main contents of the remaining chapters are as follows: Section 2 describes the ecological data model and research area; Section 3 introduces the prediction model of per capita ecological carrying capacity based on ARIMALSTM combination; Section 4 is based on the actual data collected in the Shenzhen area to achieve simulation verification; Section 5 is the conclusion and prospect of this paper
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
